Create a new custom metric definition. The metric will be added to the specified analysis package and can be used for evaluating calls.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Input for creating a new metric definition
Name of the metric
1 - 100"Customer Satisfaction"
Type of value this metric produces
COUNT, NUMERIC, BOOLEAN, SCALE, TEXT, CLASSIFICATION, OFFSET "BOOLEAN"
ID of the analysis package to add this metric to
Unique identifier for the metric (e.g. "customer_satisfaction"). Auto-generated from name if not provided.
1 - 50"customer_satisfaction"
Whether metric is global or per-participant (default: GLOBAL)
GLOBAL, PER_PARTICIPANT "GLOBAL"
Participant role to evaluate. Required when scope is PER_PARTICIPANT.
AGENT, CUSTOMER, SIMULATED_CUSTOMER, BACKGROUND_SPEAKER Which levels this metric can produce values at (default: ["CALL"])
1CALL, SEGMENT, TURN ["CALL"]LLM prompt/criteria for evaluating this metric. Used to instruct the model on how to score. Required for BOOLEAN, NUMERIC, TEXT, and SCALE types.
2000"Evaluate whether the customer expressed satisfaction with the service provided."
Label for the true/positive case (only for BOOLEAN type)
"Satisfied"
Label for the false/negative case (only for BOOLEAN type)
"Not Satisfied"
Minimum value for scale. Required for SCALE type.
0 <= x <= 1001
Maximum value for scale. Required for SCALE type.
0 <= x <= 1005
Labels for scale ranges (only for SCALE type)
Options for classification. Required for CLASSIFICATION type.
1Maximum number of classifications that can be selected (only for CLASSIFICATION type)
x >= 1The created metric definition
Metric definition data